UPDATE: [0] prefill

app.py

@@ -333,7 +333,7 @@ async def chatResponse(
     )
     logger.info(f"[REQ] {completionId} - prompt - {prompt}")
 
-    out, model_tokens, model_state = await runPrefill(request, prompt, [], model_state)
+    out, model_tokens, model_state = await runPrefill(request, prompt, [0], model_state)
 
     prefillTime = time.time()
     promptTokenCount = len(model_tokens)
@@ -415,9 +415,9 @@ async def chatResponseStream(
         else request.prompt.strip()
     )
 
-    logger.info(f"[REQ] {completionId} - context - {prompt}")
+    logger.info(f"[REQ] {completionId} - context\n```{prompt}```")
 
-    out, model_tokens, model_state = await runPrefill(request, prompt, [], model_state)
+    out, model_tokens, model_state = await runPrefill(request, prompt, [0], model_state)
 
     prefillTime = time.time()
     promptTokenCount = len(model_tokens)